INDEX

Explanations

mathematical expressions and equations

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lija

-1.50

 להיות

-1.45

じゃなくて

-1.42

"~

-1.40

 zostać

-1.38

因为他

-1.34

抬起头

-1.34

踮

-1.34

 eram

-1.32

簠

-1.32

POSITIVE LOGITS

 that

1.74

1.45

 optionally

1.38

 include

1.37

 usai

1.37

any

1.34

 могат

1.32

can

1.31

to

1.31

 with

1.24

Activations Density 0.003%